Aiming at the noises and artifacts were introduced to Synthetic Aperture Radar (SAR) image in the process of imaging and transmission, which cause many problems such as reduction of definition and lack of details, an SAR image enhancement method based on the combination of Non-Subsampled Shearlet Transform (NSST) and fuzzy contrast was proposed. Firstly, the original image was decomposed into a low-frequency component and several high-frequency components by NSST. Then, the low-frequency component was linearly stretched to improve the overall contrast, and the threshold method was adopted for high-frequency components to remove noise. And then the reconstruction image was obtained by applying the inverse NSST to the processed low-frequency and high-frequency components. Finally, fuzzy contrast method was used to improve detail information and layering of reconstruction image and obtain the final image. The experimental results on 40 images show that, compared with Histogram Equalization (HE), Multi-Scale Retinex (MSR) enhancement algorithm, Remote sensing image enhancement algorithm based on shearlet transform and multi-scale Retinex, and medical image enhancement method based on improved Gamma correction in Shearlet domain, the Peak Signal-to-Noise Ratio (PSNR) of this proposed method promotes at least 22.9%, and the Root Mean Square Error (RMSE) optimizes at least 36.2%. And finally this proposed method can obviously improve image definition and obtains clearer texture information.

Since the efficiency of rule mining and validity of recommendation are not high in personalized friends recommendation based on association rules, an improved association rule algorithm based on bitmap and hashing, namely BHA, was proposed. The mining time of frequent 2-itemsets was decreased by introducing hashing technique in this algorithm, and the irrelevant candidates were compressed to decrease the traversal of data by using bitmap and relevant properties. In addition, on the basis of BHA, a friend recommendation algorithm named STA was proposed based on similarity and trust. The problem of no displayed trust relationship in microblog was resolved effectively through trust defined by similarity of out-degree and in-degree; meanwhile, the defect of the similarity recommendation without considering users' hierarchy distance was remedied. Experiments were conducted on the user data of Sina microblog. In the comparison experiment of digging efficiency, the average minging time of BHA was only 47% of the modified AprioriTid; in the comparison experiment of availability in friend recommendation with SNFRBOAR (Social Network Friends Recommendation algorithm Based On Association Rules), the precision and recall of BHA were increased by 15.2% and 9.8% respectively. The theoretical analysis and simulation results show that STA can effectively decrease average time of mining rules, and improve the validity of friend recommendation.

Aiming at the problem that the traditional entity alignment algorithm may lead to bad performance in entity alignment task of Chinese heterogeneous encyclopedia knowledge base, an entity alignment method based on entity attributes and the features of context topics was proposed. First, a Chinese heterogeneous encyclopedia knowledge base was constructed based on Baidu encyclopedia and Hudong encyclopedia data. Next, the Resource Description Framework Schema (RDFS) vocabulary list was made to normalize the entity attributes. Then the entity context information was extracted and the Chinese word segmentation was used on the contexts. The contexts were modelled by using the topic model and the parameters were computed by Gibbs sampling method. After that the topic-word probability matrix, the characteristic word collection and the corresponding feature matrix were calculated. Last, the Longest Common Subsequence (LCS) algorithm was used to compute the entity attribute similarity. When the similarity was between the lower and the upper bounds, the topic features of the entities' context were combined to resolve the entity alignment problem. Finally, according to the standard method, an entity alignment data set of Chinese heterogeneous encyclopedia was constructed for simulation experiments. In comparison with the traditional property similarity algorithm, weighted-property algorithm, context term frequency feature model and topic model algorithm, the experimental results show that the proposed method achieves 97.8% accuracy, 88.0% recall, 92.6% F-score in people class and 98.6% accuracy, 73.0% recall, 83.9% F-score in movie class. It outperformed the other entity alignment algorithms. The experimental results also indicate that the proposed method can improve the entity alignment results in constructing the Chinese heterogeneous encyclopedia knowledge base, and it can be applied to the entity alignment tasks with context information.

Aiming at the problem of low contrast, lack of the details and weakness of edge gradient retention in remote sensing images, a new remote sensing image enhancement method based on the combination of Non-Subsampled Shearlet Transform (NSST) and guided filtering was proposed. Firstly, the input image was decomposed into a low-frequency component and several high-frequency components by NSST. Then a linear stretch was adopted for the low-frequency component to improve the overall contrast of the image, and the adaptive threshold method was used to restrain the noise in the high-frequency components. After denoising, the high-frequency components were enhanced by guided filtering to improve the detail information and edge-gradient retention ability. Finally, the final enhanced image was reconstructed by applying the inverse NSST to the processed low-frequency and high-frequency components. Experimental results show that, compared with the Histogram Equalization (HE), image enhancement based on contourlet transform and fuzzy theory, remote sensing image enhancement based on nonsubsampled contourlet transform and unsharp masking as well as remote sensing image enhancement based on non-subsampled shearlet transform and parameterized logarithmic image processing, the proposed method can effectively increase the information entropy, the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measurement (SSIM), which can obviously improve the visual effect of the image and make the texture of the image more clear.

Question classification is one of the tasks in question answering system. Since questions often have rare words and colloquial expressions, especially in the application of voice interaction, the traditional text classifications perform poorly in short question classification. Thus a short question classification algorithm was proposed, which was based on semantic extensions and used the search engine to extend knowledge for short questions, the question's category was got by selecting features with the topic model and calculating the word similarity. The experimental results show that the proposed method can get F-measure value of 0.713 in a set of 1365 real problems, which is higher than that of Support Vector Machine (SVM), K-Nearest Neighbor (KNN) algorithm and maximum entropy algorithm. Therefore, the accuracy of the question classification can be improved by above method in question answering system.

Aiming at the problem that the traditional wavelet transform, curverlet transform and contourlet transform are unable to provide the optimal sparse representation of image and can not obtain the better enhancement effect, an image enhancement algorithm based on Shearlet transform was proposed. The image was decomposed into low frequency components and high frequency components by Shearlet transform. Firstly, Multi-Scale Retinex (MSR) was used to enhance the low frequency components of Shearlet decomposition to remove the effect of illumination on image; secondly, the threshold denoising was used to suppress noise at high frequency coefficients of each scale. Finally, the fuzzy contrast enhancement method was used to the reconstruction image to improve the overall contrast of image. The experimental results show that proposed algorithm can significantly improve the image visual effect, and it has more image texture details and anti-noise capabilities. The image definition, the entropy and the Peak Signal-to-Noise Ratio (PSNR) are improved to a certain extent compared with the Histogram Equalization (HE), MSR and Fuzzy contrast enhancement in Non-Subsampled Contourlet Domain (NSCT_fuzzy) algorithms. The operation time reduces to about one half of MSR and one tenth of NSCT_fuzzy.

Concerning the low accuracy of tagging Chinese ambiguity words, a combined tagging method of rules and statistical model was proposed in this paper. Firstly, three kinds of traditional statistical models, including Hidden Markov Model (HMM), Maximum Entropy (ME) and Condition Random Field (CRF), were used to tagging problem of the ambiguity words. Then, the improved mutual information algorithm was applied to learn Part Of Speech (POS) tagging rules. Tagging rules were got through the calculation of correlation between the target words and the nearby word units. Finally, rules were combined with statistical model algorithm to tag Chinese ambiguity words. The experimental results show that after adding the rule algorithm, the average accuracy of POS tagging promotes by 5%.

The current Radio Frequency IDentification (RFID) system just simply integrates the collision algorithm and security mechanism together. Based on the analysis of classical adaptive dynamic anti-collision algorithm, an anti-collision strategy of embedded security mechanism was proposed. It combined the first traversal mechanism and Boolean mutual authentication protocol to solve the problem that traditional RFID tag identification system is not efficient and has high cost; it also has high security. Compared with the backward binary, dynamic adaptive and binary tree search algorithms, the proposed strategy can greatly reduce the times of the system search and improve the label throughput.

In order to solve the problem of insufficient training corpus for extracting attribute relation from Chinese encyclopedia, a weakly supervised method was proposed, which needed minimal human intervention. First, semi-structured attribute relations from Chinese encyclopedia entry infoboxes were used to tag entry texts for obtaining training corpus. Second, the optimized training corpus was obtained based on Naive Bayesian theory. Third, Conditional Random Field (CRF) was used to form attribute relation extraction model. The evaluation of F-score on the Hudong encyclopedia datasets was 80.9%. The experimental result shows that this method can enhance the quality of training corpus and runs a better extraction performance.